c#中过滤html的正则表达式
来源：
中文源码网 浏览：171 次 日期：2024-05-13 11:06:11
【下载文档: c#中过滤html的正则表达式.txt 】
c#中过滤html的正则表达式
实现代码
///
/// 去除HTML标记
/// ///
包括HTML的源码
///
已经去除后的文字public static string NoHTML(string Htmlstring)
{
//删除脚本
Htmlstring = Regex.Replace(Htmlstring, @"
]*?>.*?", "",
RegexOptions.IgnoreCase);
//删除HTML
Htmlstring = Regex.Replace(Htmlstring, @"<(.[^>]*)>", "",
RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"([\r\n])[\s]+", "",
RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"–>", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"Htmlstring = Regex.Replace(Htmlstring, @"&(quot|#34);", "\"",
RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(amp|#38);", "&",
RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(lt|#60);", "<",
RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(gt|#62);", ">",
RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(nbsp|#160);", " ",
RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(iexcl|#161);", "\xa1", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(cent|#162);", "\xa2", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(pound|#163);", "\xa3", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(copy|#169);", "\xa9", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&#(\d+);", "", RegexOptions.IgnoreCase);
Htmlstring.Replace("<", "");
Htmlstring.Replace(">", "");
Htmlstring.Replace("\r\n", "");
Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
return Htmlstring;
}
C#过滤Html标签及空格
public static string FilterHTML(string HTMLStr)
{
if (!string.IsNullOrEmpty(HTMLStr))
return System.Text.RegularExpressions.Regex.Replace(HTMLStr, "<[^>]*>| ", "");
else
return "";
}
写一个静态方法移除HTML标签
#region
///
/// 移除HTML标签
///
/// HTMLStr
public static string ParseTags(string HTMLStr)
{
return System.Text.RegularExpressions.Regex.Replace(HTMLStr, "<[^>]*>", "");
}
#endregion
取出文本中的图片地址
#region
///
/// 取出文本中的图片地址
///
/// HTMLStr
public static string GetImgUrl(string HTMLStr)
{
string str = string.Empty;
string sPattern = @"^]*>";
Regex r = new Regex(@"]*\s*src\s*=\s*([']?)(?\S+)'?[^>]*>",
RegexOptions.Compiled);
Match m = r.Match(HTMLStr.ToLower());
if (m.Success)
str = m.Result("${url}");
return str;
}
#endregion
提取HTML代码中文字的C#函数
///
/// 提取HTML代码中文字的C#函数
///
/// 包括HTML的源码
/// 已经去除后的文字
using System;
using System.Text.RegularExpressions;
public class StripHTMLTest
{
public static void Main()
{
string s = StripHTML(
"中国石龙信息平台faddfs龙信息平台");
Console.WriteLine(s);
}
public static string StripHTML(string strHtml)
{
string[]aryReg =
{
@"]*?>.*?",
@"<(\/\s*)?!?((\w+:)?\w+)(\w+(\s*=?\s*(([""'])(\\["
"'tbnr]|[^\7])*?\7|\w+)|.{0})|\s)*?(\/\s*)?>", @"([\r\n])[\s]+", @
"&(quot|#34);", @"&(amp|#38);", @"&(lt|#60);", @"&(gt|#62);", @
"&(nbsp|#160);", @"&(iexcl|#161);", @"&(cent|#162);", @"&(pound|#163);",
@"&(copy|#169);", @"&#(\d+);", @"-->", @"
